© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19826
    Prev
    Next
    INDEX
    Explanations

    code snippets and math problems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    phia
    -0.09
     Rady
    -0.09
    æ¤Ĵ
    -0.08
    æĺ¯æĪij们çļĦ
    -0.08
    ?key
    -0.08
    asty
    -0.08
    éĥ½æĺ¯ä¸ĢäºĽ
    -0.07
    alez
    -0.07
    å¤ļéħļ
    -0.07
    人ä¹ĭ
    -0.07
    POSITIVE LOGITS
    缸åħ³èµĦæĸĻ
    0.07
    uler
    0.06
    m
    0.06
    çļĦ说æ³ķ
    0.06
    æŃ£ç¡®çļĦæĺ¯
    0.06
    pat
    0.06
    计价
    0.06
    ernel
    0.06
    olini
    0.06
     déficit
    0.06
    Activations Density 0.001%

    No Known Activations